/**
 * Vector similarity calculation utilities for embedding comparison
 * From AIU implementation - enables semantic analysis of chat messages
 */
export interface SimilarityMetrics {
    cosineSimilarity: number;
    euclideanDistance: number;
    dotProduct: number;
    manhattanDistance: number;
}
/**
 * Calculate cosine similarity between two vectors
 * Returns a value between -1 and 1, where 1 means identical direction
 */
export declare function cosineSimilarity(a: number[], b: number[]): number;
/**
 * Calculate Euclidean distance between two vectors
 * Lower values indicate more similar vectors (0 = identical)
 */
export declare function euclideanDistance(a: number[], b: number[]): number;
/**
 * Calculate dot product of two vectors
 * Higher values indicate more similarity
 */
export declare function dotProduct(a: number[], b: number[]): number;
/**
 * Calculate Manhattan distance (L1 norm) between two vectors
 * Lower values indicate more similar vectors (0 = identical)
 */
export declare function manhattanDistance(a: number[], b: number[]): number;
/**
 * Calculate all similarity metrics between two vectors
 */
export declare function calculateAllMetrics(a: number[], b: number[]): SimilarityMetrics;
/**
 * Format a metric value for display
 */
export declare function formatMetric(value: number, metric: keyof SimilarityMetrics): string;
/**
 * Get human-readable description of metric
 */
export declare function getMetricDescription(metric: keyof SimilarityMetrics): string;
//# sourceMappingURL=similarity.d.ts.map